Image OCR
Extract text (English, Greek and 15 more languages) from an image with OCR that runs in your browser.
Runs in your browser Your input never leaves your device.
Pick the language first: the engine only reads the language you choose. Its data downloads once, then your browser keeps it.
Drop an image here, or .
Report a problem with this tool
About this tool
Pull text out of a screenshot, scan or photo of a document. The tool uses Tesseract (tesseract.js), an open-source OCR engine, set to English. The first time you run it, your browser loads the OCR engine from this site and downloads the language data from a CDN, which takes a moment, and then recognition runs locally; your image is not uploaded. Progress is shown, and the result appears in a text box with a Copy button. Accuracy is best on sharp, high-contrast, straight printed text. It is weak on handwriting, decorative fonts, tilted pages and small, blurry text.
How to use it
- Drop an image or choose a file.
- Wait for the engine to load and the progress bar to finish.
- Read the extracted text.
- Press Copy.
Common problems
- Output is garbled
- Use a larger, sharper image with dark text on a light background, and straighten it first.
- Non-English text is wrong
- Only the English language model is loaded, so other scripts and accented letters are unreliable.
- Stuck on loading
- The engine files come from a CDN, so an offline connection or a blocker may stop them. Check your connection and retry.